Files
superpowers/skills/brainstorming/scripts/server.cjs
Jesse Vincent e3fe480b29 feat(brainstorm-server): gate every endpoint behind a per-session key
The companion server is reachable by any local browser tab (default loopback
bind) and by any host that can route to it (remote --host bind). It served
screens, files, and accepted event-injecting WebSocket connections with no
authentication, so a malicious browser tab or a direct remote client could read
brainstorm content or inject events that the agent reads as the user's input
(prompt injection into a live session).

Generate a per-session secret token, carry it in the served URL as ?key=, and
mirror it into an HttpOnly SameSite=Strict per-port cookie on first load so
same-origin subresources and the WebSocket handshake authenticate automatically.
Every HTTP request and WebSocket upgrade now requires a valid key (query or
cookie, constant-time compared); unauthenticated requests get a friendly 403
explaining they need the full URL. A secret authenticates the client uniformly
across loopback, tunnel, and remote binds and defeats DNS rebinding, which a
Host/Origin allowlist cannot.

Also guard handleMessage against a null JSON payload that crashed the process.

Tests: new auth.test.js (13 cases) covering the key on /, /files/*, and WS plus
cookie bootstrap and the null-payload guard; server.test.js threads the key;
ws-protocol.test.js + auth.test.js wired into npm test.

Closes #1014
Refs #1110, #1553, #1504
2026-06-09 18:29:49 -07:00

520 lines
18 KiB
JavaScript

const crypto = require('crypto');
const http = require('http');
const fs = require('fs');
const path = require('path');
// ========== WebSocket Protocol (RFC 6455) ==========
const OPCODES = { TEXT: 0x01, CLOSE: 0x08, PING: 0x09, PONG: 0x0A };
const WS_MAGIC = '258EAFA5-E914-47DA-95CA-C5AB0DC85B11';
const MAX_FRAME_PAYLOAD_BYTES = 10 * 1024 * 1024;
function computeAcceptKey(clientKey) {
return crypto.createHash('sha1').update(clientKey + WS_MAGIC).digest('base64');
}
function encodeFrame(opcode, payload) {
const fin = 0x80;
const len = payload.length;
let header;
if (len < 126) {
header = Buffer.alloc(2);
header[0] = fin | opcode;
header[1] = len;
} else if (len < 65536) {
header = Buffer.alloc(4);
header[0] = fin | opcode;
header[1] = 126;
header.writeUInt16BE(len, 2);
} else {
header = Buffer.alloc(10);
header[0] = fin | opcode;
header[1] = 127;
header.writeBigUInt64BE(BigInt(len), 2);
}
return Buffer.concat([header, payload]);
}
function decodeFrame(buffer) {
if (buffer.length < 2) return null;
const secondByte = buffer[1];
const opcode = buffer[0] & 0x0F;
const masked = (secondByte & 0x80) !== 0;
let payloadLen = secondByte & 0x7F;
let offset = 2;
if (!masked) throw new Error('Client frames must be masked');
if (payloadLen === 126) {
if (buffer.length < 4) return null;
payloadLen = buffer.readUInt16BE(2);
offset = 4;
} else if (payloadLen === 127) {
if (buffer.length < 10) return null;
const extendedLen = buffer.readBigUInt64BE(2);
if (extendedLen > BigInt(MAX_FRAME_PAYLOAD_BYTES)) {
throw new Error('WebSocket frame payload exceeds maximum allowed size');
}
payloadLen = Number(extendedLen);
offset = 10;
}
if (payloadLen > MAX_FRAME_PAYLOAD_BYTES) {
throw new Error('WebSocket frame payload exceeds maximum allowed size');
}
const maskOffset = offset;
const dataOffset = offset + 4;
const totalLen = dataOffset + payloadLen;
if (buffer.length < totalLen) return null;
const mask = buffer.slice(maskOffset, dataOffset);
const data = Buffer.alloc(payloadLen);
for (let i = 0; i < payloadLen; i++) {
data[i] = buffer[dataOffset + i] ^ mask[i % 4];
}
return { opcode, payload: data, bytesConsumed: totalLen };
}
// ========== Configuration ==========
const PORT_FILE = process.env.BRAINSTORM_PORT_FILE || null;
const randomPort = () => 49152 + Math.floor(Math.random() * 16383);
// Prefer an explicit port, else the port this session last bound (so a restart
// reuses it and an already-open browser tab reconnects), else a random high port.
function preferredPort() {
if (process.env.BRAINSTORM_PORT) return Number(process.env.BRAINSTORM_PORT);
if (PORT_FILE) {
try {
const p = Number(fs.readFileSync(PORT_FILE, 'utf-8').trim());
if (Number.isInteger(p) && p > 1023 && p < 65536) return p;
} catch (e) { /* no prior port recorded */ }
}
return randomPort();
}
let PORT = preferredPort();
const HOST = process.env.BRAINSTORM_HOST || '127.0.0.1';
const URL_HOST = process.env.BRAINSTORM_URL_HOST || (HOST === '127.0.0.1' ? 'localhost' : HOST);
const SESSION_DIR = process.env.BRAINSTORM_DIR || '/tmp/brainstorm';
const CONTENT_DIR = path.join(SESSION_DIR, 'content');
const STATE_DIR = path.join(SESSION_DIR, 'state');
let ownerPid = process.env.BRAINSTORM_OWNER_PID ? Number(process.env.BRAINSTORM_OWNER_PID) : null;
// Per-session secret key. The companion is reachable by any local browser tab
// and, when bound to a non-loopback host, by any host that can route to it.
// The key authenticates the real client uniformly across loopback, tunnel, and
// remote binds — and defeats DNS rebinding — where a Host/Origin allowlist
// cannot. It rides the served URL as ?key= and is mirrored into a cookie on
// first load so same-origin subresources and the WebSocket carry it for free.
const TOKEN = process.env.BRAINSTORM_TOKEN || crypto.randomBytes(32).toString('hex');
const COOKIE_NAME = 'brainstorm-key-' + PORT;
const MIME_TYPES = {
'.html': 'text/html', '.css': 'text/css', '.js': 'application/javascript',
'.json': 'application/json', '.png': 'image/png', '.jpg': 'image/jpeg',
'.jpeg': 'image/jpeg', '.gif': 'image/gif', '.svg': 'image/svg+xml'
};
// ========== Templates and Constants ==========
const WAITING_PAGE = `<!DOCTYPE html>
<html>
<head><meta charset="utf-8"><title>Brainstorm Companion</title>
<style>body { font-family: system-ui, sans-serif; padding: 2rem; max-width: 800px; margin: 0 auto; }
h1 { color: #333; } p { color: #666; }</style>
</head>
<body><h1>Brainstorm Companion</h1>
<p>Waiting for the agent to push a screen...</p></body></html>`;
const FORBIDDEN_PAGE = `<!DOCTYPE html>
<html>
<head><meta charset="utf-8"><title>Session key required</title>
<style>body { font-family: system-ui, sans-serif; padding: 2rem; max-width: 800px; margin: 0 auto; }
h1 { color: #333; } p { color: #666; } code { background: #f0f0f0; padding: 0.1em 0.3em; border-radius: 4px; }</style>
</head>
<body><h1>Session key required</h1>
<p>This page needs the full URL your coding agent gave you, including the
<code>?key=&hellip;</code> part. Copy the complete URL and open it again.</p></body></html>`;
const frameTemplate = fs.readFileSync(path.join(__dirname, 'frame-template.html'), 'utf-8');
const helperScript = fs.readFileSync(path.join(__dirname, 'helper.js'), 'utf-8');
const helperInjection = '<script>\n' + helperScript + '\n</script>';
// ========== Helper Functions ==========
function isFullDocument(html) {
const trimmed = html.trimStart().toLowerCase();
return trimmed.startsWith('<!doctype') || trimmed.startsWith('<html');
}
function wrapInFrame(content) {
return frameTemplate.replace('<!-- CONTENT -->', content);
}
function getNewestScreen() {
const files = fs.readdirSync(CONTENT_DIR)
.filter(f => !f.startsWith('.') && f.endsWith('.html'))
.map(f => {
const fp = path.join(CONTENT_DIR, f);
return { path: fp, mtime: fs.statSync(fp).mtime.getTime() };
})
.sort((a, b) => b.mtime - a.mtime);
return files.length > 0 ? files[0].path : null;
}
// ========== Authentication ==========
function timingSafeEqualStr(a, b) {
const ab = Buffer.from(String(a));
const bb = Buffer.from(String(b));
if (ab.length !== bb.length) return false;
return crypto.timingSafeEqual(ab, bb);
}
function parseCookies(header) {
const out = {};
if (!header) return out;
for (const part of header.split(';')) {
const eq = part.indexOf('=');
if (eq < 0) continue;
out[part.slice(0, eq).trim()] = part.slice(eq + 1).trim();
}
return out;
}
// A request is authorized if it carries the session key as ?key= or as the
// session cookie. Both are compared in constant time.
function isAuthorized(req) {
const q = req.url.indexOf('?');
if (q >= 0) {
const key = new URLSearchParams(req.url.slice(q + 1)).get('key');
if (key && timingSafeEqualStr(key, TOKEN)) return true;
}
const cookie = parseCookies(req.headers['cookie'])[COOKIE_NAME];
if (cookie && timingSafeEqualStr(cookie, TOKEN)) return true;
return false;
}
function pathnameOf(url) {
const q = url.indexOf('?');
return q >= 0 ? url.slice(0, q) : url;
}
// ========== HTTP Request Handler ==========
function handleRequest(req, res) {
touchActivity();
if (!isAuthorized(req)) {
res.writeHead(403, { 'Content-Type': 'text/html; charset=utf-8' });
res.end(FORBIDDEN_PAGE);
return;
}
// Mirror the key into a cookie so same-origin subresources (/files/*) and the
// WebSocket handshake carry it automatically, whatever URL style the agent
// writes. SameSite=Strict: a cross-site page can neither read the key nor ride
// the cookie; HttpOnly: page scripts can't exfiltrate it.
res.setHeader('Set-Cookie',
COOKIE_NAME + '=' + TOKEN + '; HttpOnly; SameSite=Strict; Path=/');
const pathname = pathnameOf(req.url);
if (req.method === 'GET' && pathname === '/') {
const screenFile = getNewestScreen();
let html = screenFile
? (raw => isFullDocument(raw) ? raw : wrapInFrame(raw))(fs.readFileSync(screenFile, 'utf-8'))
: WAITING_PAGE;
if (html.includes('</body>')) {
html = html.replace('</body>', helperInjection + '\n</body>');
} else {
html += helperInjection;
}
res.writeHead(200, { 'Content-Type': 'text/html; charset=utf-8' });
res.end(html);
} else if (req.method === 'GET' && pathname.startsWith('/files/')) {
const fileName = path.basename(pathname.slice(7));
const filePath = path.join(CONTENT_DIR, fileName);
if (fileName.startsWith('.') || !fs.existsSync(filePath)) {
res.writeHead(404);
res.end('Not found');
return;
}
const ext = path.extname(filePath).toLowerCase();
const contentType = MIME_TYPES[ext] || 'application/octet-stream';
res.writeHead(200, { 'Content-Type': contentType });
res.end(fs.readFileSync(filePath));
} else {
res.writeHead(404);
res.end('Not found');
}
}
// ========== WebSocket Connection Handling ==========
const clients = new Set();
function handleUpgrade(req, socket) {
if (!isAuthorized(req)) { socket.destroy(); return; }
const key = req.headers['sec-websocket-key'];
if (!key) { socket.destroy(); return; }
const accept = computeAcceptKey(key);
socket.write(
'HTTP/1.1 101 Switching Protocols\r\n' +
'Upgrade: websocket\r\n' +
'Connection: Upgrade\r\n' +
'Sec-WebSocket-Accept: ' + accept + '\r\n\r\n'
);
let buffer = Buffer.alloc(0);
clients.add(socket);
socket.on('data', (chunk) => {
buffer = Buffer.concat([buffer, chunk]);
while (buffer.length > 0) {
let result;
try {
result = decodeFrame(buffer);
} catch (e) {
socket.end(encodeFrame(OPCODES.CLOSE, Buffer.alloc(0)));
clients.delete(socket);
return;
}
if (!result) break;
buffer = buffer.slice(result.bytesConsumed);
switch (result.opcode) {
case OPCODES.TEXT:
handleMessage(result.payload.toString());
break;
case OPCODES.CLOSE:
socket.end(encodeFrame(OPCODES.CLOSE, Buffer.alloc(0)));
clients.delete(socket);
return;
case OPCODES.PING:
socket.write(encodeFrame(OPCODES.PONG, result.payload));
break;
case OPCODES.PONG:
break;
default: {
const closeBuf = Buffer.alloc(2);
closeBuf.writeUInt16BE(1003);
socket.end(encodeFrame(OPCODES.CLOSE, closeBuf));
clients.delete(socket);
return;
}
}
}
});
socket.on('close', () => clients.delete(socket));
socket.on('error', () => clients.delete(socket));
}
function handleMessage(text) {
let event;
try {
event = JSON.parse(text);
} catch (e) {
console.error('Failed to parse WebSocket message:', e.message);
return;
}
touchActivity();
console.log(JSON.stringify({ source: 'user-event', ...event }));
if (event && event.choice) {
const eventsFile = path.join(STATE_DIR, 'events');
fs.appendFileSync(eventsFile, JSON.stringify(event) + '\n');
}
}
function broadcast(msg) {
const frame = encodeFrame(OPCODES.TEXT, Buffer.from(JSON.stringify(msg)));
for (const socket of clients) {
try { socket.write(frame); } catch (e) { clients.delete(socket); }
}
}
// Best-effort: open the user's browser the first time a screen is actually ready
// to show. Skips when disabled, on a non-loopback (remote) bind, or when a
// browser is already connected. Override the launcher with BRAINSTORM_OPEN_CMD.
let browserOpened = false;
function maybeOpenBrowser() {
if (browserOpened) return;
browserOpened = true;
if (!process.env.BRAINSTORM_OPEN) return; // opt-in: only after the user approves the companion
if (HOST !== '127.0.0.1' && HOST !== 'localhost') return;
if (clients.size > 0) return; // the user already opened it
const url = 'http://' + URL_HOST + ':' + PORT;
const cp = require('child_process');
// Operator-provided launcher: run as given (this env var is trusted operator input).
if (process.env.BRAINSTORM_OPEN_CMD) {
try { cp.exec(process.env.BRAINSTORM_OPEN_CMD + ' ' + JSON.stringify(url), () => {}); } catch (e) { /* best effort */ }
return;
}
// Platform launchers: pass the URL as an argv element via execFile (no shell),
// so a url-host containing shell metacharacters can't inject a command.
const isWSL = process.platform === 'linux' && /microsoft/i.test(require('os').release());
let bin, args;
if (process.platform === 'darwin') { bin = 'open'; args = [url]; }
else if (process.platform === 'win32' || isWSL) { bin = 'cmd.exe'; args = ['/c', 'start', '', url]; }
else if (process.env.DISPLAY || process.env.WAYLAND_DISPLAY) { bin = 'xdg-open'; args = [url]; }
else return; // headless: nothing to open
try { cp.execFile(bin, args, () => {}); } catch (e) { /* best effort */ }
}
// ========== Activity Tracking ==========
// Idle timeout: shut down after this long with no activity. Default 4 hours;
// override with BRAINSTORM_IDLE_TIMEOUT_MS (start-server.sh: --idle-timeout-minutes).
const IDLE_TIMEOUT_MS = (() => {
const ms = Number(process.env.BRAINSTORM_IDLE_TIMEOUT_MS);
return Number.isFinite(ms) && ms > 0 ? ms : 4 * 60 * 60 * 1000;
})();
// How often the watchdog checks for owner-death / idleness. Configurable mainly
// so tests can run fast; production default is 60s.
const LIFECYCLE_CHECK_MS = (() => {
const ms = Number(process.env.BRAINSTORM_LIFECYCLE_CHECK_MS);
return Number.isFinite(ms) && ms > 0 ? ms : 60 * 1000;
})();
let lastActivity = Date.now();
function touchActivity() {
lastActivity = Date.now();
}
// ========== File Watching ==========
const debounceTimers = new Map();
// ========== Server Startup ==========
function startServer() {
if (!fs.existsSync(CONTENT_DIR)) fs.mkdirSync(CONTENT_DIR, { recursive: true });
if (!fs.existsSync(STATE_DIR)) fs.mkdirSync(STATE_DIR, { recursive: true });
// Track known files to distinguish new screens from updates.
// macOS fs.watch reports 'rename' for both new files and overwrites,
// so we can't rely on eventType alone.
const knownFiles = new Set(
fs.readdirSync(CONTENT_DIR).filter(f => !f.startsWith('.') && f.endsWith('.html'))
);
const server = http.createServer(handleRequest);
server.on('upgrade', handleUpgrade);
const watcher = fs.watch(CONTENT_DIR, (eventType, filename) => {
if (!filename || filename.startsWith('.') || !filename.endsWith('.html')) return;
if (debounceTimers.has(filename)) clearTimeout(debounceTimers.get(filename));
debounceTimers.set(filename, setTimeout(() => {
debounceTimers.delete(filename);
const filePath = path.join(CONTENT_DIR, filename);
if (!fs.existsSync(filePath)) return; // file was deleted
touchActivity();
if (!knownFiles.has(filename)) {
knownFiles.add(filename);
const eventsFile = path.join(STATE_DIR, 'events');
if (fs.existsSync(eventsFile)) fs.unlinkSync(eventsFile);
console.log(JSON.stringify({ type: 'screen-added', file: filePath }));
maybeOpenBrowser();
} else {
console.log(JSON.stringify({ type: 'screen-updated', file: filePath }));
}
broadcast({ type: 'reload' });
}, 100));
});
watcher.on('error', (err) => console.error('fs.watch error:', err.message));
function shutdown(reason) {
console.log(JSON.stringify({ type: 'server-stopped', reason }));
const infoFile = path.join(STATE_DIR, 'server-info');
if (fs.existsSync(infoFile)) fs.unlinkSync(infoFile);
fs.writeFileSync(
path.join(STATE_DIR, 'server-stopped'),
JSON.stringify({ reason, timestamp: Date.now() }) + '\n'
);
watcher.close();
clearInterval(lifecycleCheck);
// Close any upgraded WebSocket sockets so server.close() can complete and
// the process actually exits instead of lingering on an open connection.
for (const socket of clients) {
try { socket.destroy(); } catch (e) { /* already gone */ }
}
server.close(() => process.exit(0));
}
function ownerAlive() {
if (!ownerPid) return true;
try { process.kill(ownerPid, 0); return true; } catch (e) { return e.code === 'EPERM'; }
}
// Periodically exit if the owner process died or we've been idle too long.
const lifecycleCheck = setInterval(() => {
if (!ownerAlive()) shutdown('owner process exited');
else if (Date.now() - lastActivity > IDLE_TIMEOUT_MS) shutdown('idle timeout');
}, LIFECYCLE_CHECK_MS);
lifecycleCheck.unref();
// Validate owner PID at startup. If it's already dead, the PID resolution
// was wrong (common on WSL, Tailscale SSH, and cross-user scenarios).
// Disable monitoring and rely on the idle timeout instead.
if (ownerPid) {
try { process.kill(ownerPid, 0); }
catch (e) {
if (e.code !== 'EPERM') {
console.log(JSON.stringify({ type: 'owner-pid-invalid', pid: ownerPid, reason: 'dead at startup' }));
ownerPid = null;
}
}
}
// If the preferred port is already taken (e.g. a previous server is still
// alive), fall back to a random port once instead of failing.
let triedFallback = false;
function onListen() {
// Record the bound port so the next restart of this session reuses it — but
// ONLY when we got our preferred port. On a fallback we bound a *different*
// port because someone else holds the preferred one; persisting it would
// overwrite the shared .last-port and strand that other session's open tab.
if (PORT_FILE && !triedFallback) {
try { fs.writeFileSync(PORT_FILE, String(PORT)); } catch (e) { /* best effort */ }
}
const info = JSON.stringify({
type: 'server-started', port: Number(PORT), host: HOST,
url_host: URL_HOST, url: 'http://' + URL_HOST + ':' + PORT + '/?key=' + TOKEN,
screen_dir: CONTENT_DIR, state_dir: STATE_DIR, idle_timeout_ms: IDLE_TIMEOUT_MS
});
console.log(info);
fs.writeFileSync(path.join(STATE_DIR, 'server-info'), info + '\n');
}
server.on('error', (err) => {
if (err.code === 'EADDRINUSE' && !triedFallback) {
triedFallback = true;
PORT = randomPort();
server.listen(PORT, HOST, onListen);
} else {
console.error('Server failed to bind:', err.message);
process.exit(1);
}
});
server.listen(PORT, HOST, onListen);
}
if (require.main === module) {
startServer();
}
module.exports = { computeAcceptKey, encodeFrame, decodeFrame, OPCODES, MAX_FRAME_PAYLOAD_BYTES };